Skip to main content

Questions tagged [corpus-linguistics]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
19 views

Random sample of the search result?

I am looking at how the word maybe is used in COCA. As I want to analyze the contexts it occurs in, I need to random-sample the search result (which is around 374K hits), so that I can see in what ...
Yuka's user avatar
  • 11
-1 votes
0 answers
20 views

How to analyze text in terms of emotive/emotional language?

I have a text (a number of them), generated by AI. I want to analyze the emotive/emotional language, as well as investigate the criteria proposed by LIWC Dimension (positive tone, allure, moralization)...
Vera's user avatar
  • 1
3 votes
0 answers
24 views

Automatic annotation of *non-native* semi-spontaneous speech

I wonder if there is any tool for automatically annotating L2-semi-spontaneous speech (practically said, to produce a TextGrid file from a sound file (.wav) and a text file containing the ...
uniuser's user avatar
  • 31
1 vote
0 answers
30 views

Is there a way for random term extraction when searching COCA (the Corpus of Contemporary American English)?

When I search for 1000 examples of maybe using COCA data, most of the data that comes up is from older years. How can I obtain data that is randomly extracted based on the era in which it was used, ...
Yuka's user avatar
  • 11
0 votes
0 answers
25 views

Error Tagging in Corpus from English Language Learners

Is there anyone here with experience using the Louvain Error Tagging system (ideally, on English text in an L2 corpus?) I'm trying to learn it and would love to have someone to bounce questions and ...
Act3Linguist's user avatar
0 votes
1 answer
43 views

Ideal number of randomized concordancing lines

I want to perform randomized concordancing on a news corpus with 807 mil. tokens from 2 mil. documents from 2011-2022. Is there any ideal number of concordancing in order to be able to make a ...
pindakazen's user avatar
0 votes
0 answers
24 views

Is plain orthographic transciption of speech recordings adequate for corpus creation?

NOTE: I am not a linguist, but my interest is in the Natural Language Processing (NLP) field. I am doing a research which is focused only on gathering new or distinct words on a recently described ...
Rod Maniego's user avatar
0 votes
0 answers
22 views

Are open-ended questions allowed for an interview focused on corpus creation?

NOTE: I am not a linguist, but my interest is in the Natural Language Processing (NLP) field. I am doing a research which is focused only on gathering new or distinct words on a recently described ...
Rod Maniego's user avatar
-1 votes
2 answers
75 views

Do I need to lemmatize my corpus when performing collocation analysis on inflective languages?

Do I need to lemmatize my corpus when I am going to perform a collocational analysis? Several language, including English, are to a certain extent inflective. These inflections sometimes carries ...
pindakazen's user avatar
1 vote
0 answers
64 views

What differentiates the usage of MI and MI3 in collocation analysis?

In Brezina (2018), it is stated that to measure collocation strength, one may use the Mutual Information (MI) to test the collocational strength of a given collocation. MI is naturally more sensitive ...
pindakazen's user avatar
0 votes
1 answer
36 views

What does the word "company" mean in the context of collocation analysis in corpus linguistics?

I am currently reading Brezina (2018) on Statistics in Corpus Linguistics. I have a hard time trying to decipher what the author means of "company" in this sentence: Dice and log Dice, and ...
pindakazen's user avatar
0 votes
0 answers
45 views

WordSmith or Antcoc?

[Corpus linguistics] [Software recommendation] Hi guys, I have a small corpus I wish to analyze using a frequency list I have in order to extract vocabulary. What I want to do is: Compare the words ...
Regina Paredes's user avatar
0 votes
1 answer
55 views

Corpus Linguistics Major [closed]

I want to use corpus in my MA research, but I have a large problem; how can I analyze the data? Do I use software corpora or corpus such as BNC? I know it is according to my research question, but ...
Yous Gaber's user avatar
-2 votes
1 answer
66 views

How could you study “cultural differences” using corpora? [closed]

Anyone who’s traveled has come upon a sense of there being some “cultural differences”, but my mind is always seeking to systematize things, and I’ve wondered if there is a better way to collect tons ...
Julius Hamilton's user avatar